Stereo matching with Global Edge Constraint and Graph Cuts

We propose a novel method on stereo matching based on the Global Edge Constraint (GEC) and Graph Cuts. Firstly, the GEC composed of particular image edges is employed to generate the initial disparity maps. And then the reliable disparity maps consistent with the observed data are extracted to construct the data term of the energy function. Finally, we incorporate the GEC as a soft constraint into our global optimization framework, and the optimal solution could be approximated via graph cuts. Experimental results demonstrated the good performance of our proposed approach.